Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    explicitly telling or stating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Analyzing
    0.48
    Analyzing
    0.46
    利用
    0.45
     பற்றிய
    0.43
     analyzing
    0.42
     получают
    0.40
    Analyze
    0.39
     отрима
    0.39
     entwickelt
    0.39
     analyze
    0.38
    POSITIVE LOGITS
     mengatakan
    1.59
     saying
    1.49
    告诉
    1.47
    บอก
    1.46
     tell
    1.41
     telling
    1.36
     tells
    1.35
     บอก
    1.30
     told
    1.28
     stating
    1.28
    Act Density 0.076%

    No Known Activations